Coderl: Mastering code generation through pretrained models and deep reinforcement learning
Program synthesis or code generation aims to generate a program that satisfies a problem
specification. Recent approaches using large-scale pretrained language models (LMs) have …
specification. Recent approaches using large-scale pretrained language models (LMs) have …
Competition-level code generation with alphacode
Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist
programmers or even generate programs themselves could make programming more …
programmers or even generate programs themselves could make programming more …
Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit
Code intelligence leverages machine learning techniques to extract knowledge from
extensive code corpora, with the aim of developing intelligent tools to improve the quality …
extensive code corpora, with the aim of developing intelligent tools to improve the quality …
Reacc: A retrieval-augmented code completion framework
Code completion, which aims to predict the following code token (s) according to the code
context, can improve the productivity of software development. Recent work has proved that …
context, can improve the productivity of software development. Recent work has proved that …
Grounded copilot: How programmers interact with code-generating models
Powered by recent advances in code-generating models, AI assistants like Github Copilot
promise to change the face of programming forever. But what is this new face of …
promise to change the face of programming forever. But what is this new face of …
Codescore: Evaluating code generation by learning code execution
A proper code evaluation metric (CEM) profoundly impacts the evolution of code generation,
which is an important research field in NLP and software engineering. Prevailing match …
which is an important research field in NLP and software engineering. Prevailing match …
Think outside the code: Brainstorming boosts large language models in code generation
Code generation aims to automatically generate source code from high-level task
specifications, which can significantly increase productivity of software engineering …
specifications, which can significantly increase productivity of software engineering …
Domain adaptive code completion via language models and decoupled domain databases
Large Language Models (LLMs) have demonstrated remarkable performance in code
completion. However, due to the lack of domain-specific knowledge, they may not be optimal …
completion. However, due to the lack of domain-specific knowledge, they may not be optimal …
Reinforcement learning from automatic feedback for high-quality unit test generation
B Steenhoek, M Tufano, N Sundaresan… - arXiv preprint arXiv …, 2023 - arxiv.org
Software testing is a crucial aspect of software development, and the creation of high-quality
tests that adhere to best practices is essential for effective maintenance. Recently, Large …
tests that adhere to best practices is essential for effective maintenance. Recently, Large …
Detect-localize-repair: A unified framework for learning to debug with codet5
Automated software debugging is a crucial task for improving the productivity of software
developers. Many neural-based techniques have been proven effective for debugging …
developers. Many neural-based techniques have been proven effective for debugging …